[7.6.3] -- [FEAT][Agent.run() acceleration] [FIX][Groupchat]

Author: kyegomez

.env.example

@@ -29,8 +29,6 @@ BRAVESEARCH_API_KEY=""
 TAVILY_API_KEY=""
 YOU_API_KEY=""
 
-## Analytics & Monitoring
-AGENTOPS_API_KEY=""
 EXA_API_KEY=""
 
 ## Browser Automation

README.md

@@ -427,8 +427,6 @@ We provide vast array of features to save agent states using json, yaml, toml, u
 | `tokens_checks()` | Performs token checks for the agent. |
 | `print_dashboard()` | Prints the dashboard of the agent. |
 | `get_docs_from_doc_folders()` | Fetches all the documents from the doc folders. |
-| `activate_agentops()` | Activates agent operations. |
-| `check_end_session_agentops()` | Checks the end of the session for agent operations. |
 
 
 
@@ -480,8 +478,6 @@ agent.print_dashboard()
 agent.get_docs_from_doc_folders()
 
 # Activate agent ops
-agent.activate_agentops()
-agent.check_end_session_agentops()
 
 # Dump the model to a JSON file
 agent.model_dump_json()

agent_tools_dict_example.py

@@ -4,7 +4,7 @@
 from swarms.prompts.finance_agent_sys_prompt import (
     FINANCIAL_AGENT_SYS_PROMPT,
 )
-from swarms.utils.str_to_dict import str_to_dict
+
 
 load_dotenv()
 
@@ -49,16 +49,11 @@
     system_prompt=FINANCIAL_AGENT_SYS_PROMPT,
     max_loops=1,
     tools_list_dictionary=tools,
+    output_type="final",
 )
 
 out = agent.run(
     "What is the current stock price for Apple Inc. (AAPL)? Include historical price data.",
 )
 
-print(out)
-
 print(type(out))
-
-print(str_to_dict(out))
-
-print(type(str_to_dict(out)))

docs/applications/discord.md

@@ -45,6 +45,7 @@ plugins:
   #     include_requirejs: true
 extra_css:
   - assets/css/extra.css
+
 extra:
   social:
     - icon: fontawesome/brands/twitter
@@ -60,6 +61,20 @@ extra:
     provider: google
     property: G-MPE9C65596
 
+  alternate:
+    - name: English
+      link: /
+      lang: en
+    - name: 简体中文
+      link: /zh/
+      lang: zh
+    - name: 日本語
+      link: /ja/
+      lang: ja
+    - name: 한국어
+      link: /ko/
+      lang: ko
+
 theme:
   name: material
   custom_dir: overrides
@@ -90,6 +105,23 @@ theme:
     code: "Fira Code"      # Modern look for code snippets
 
 
+  # Add language selector
+  language: en
+  alternate:
+    - name: English
+      link: /
+      lang: en
+    - name: 简体中文
+      link: /zh/
+      lang: zh
+    - name: 日本語
+      link: /ja/
+      lang: ja
+    - name: 한국어
+      link: /ko/
+      lang: ko
+
+
 # Extensions
 markdown_extensions:
   - abbr

docs/blogs/blog.md

@@ -58,7 +58,6 @@ Swarms uses environment variables for configuration management and secure creden
    - `YOU_API_KEY`: You.com search integration
 
 2. **Analytics & Monitoring**
-   - `AGENTOPS_API_KEY`: AgentOps monitoring
    - `EXA_API_KEY`: Exa.ai services
 
 3. **Browser Automation**

docs/mkdocs.yml

@@ -183,7 +183,6 @@ graph TD
 | `remove_tool(tool)` | Removes a tool from the agent's toolset. | `tool` (Callable): Tool to remove. | `agent.remove_tool(my_custom_tool)` |
 | `remove_tools(tools)` | Removes multiple tools from the agent's toolset. | `tools` (List[Callable]): List of tools to remove. | `agent.remove_tools([tool1, tool2])` |
 | `get_docs_from_doc_folders()` | Retrieves and processes documents from the specified folder. | None | `agent.get_docs_from_doc_folders()` |
-| `check_end_session_agentops()` | Checks and ends the AgentOps session if enabled. | None | `agent.check_end_session_agentops()` |
 | `memory_query(task, *args, **kwargs)` | Queries the long-term memory for relevant information. | `task` (str): The task or query.<br>`*args`, `**kwargs`: Additional arguments. | `result = agent.memory_query("Find information about X")` |
 | `sentiment_analysis_handler(response)` | Performs sentiment analysis on the given response. | `response` (str): The response to analyze. | `agent.sentiment_analysis_handler("Great job!")` |
 | `count_and_shorten_context_window(history, *args, **kwargs)` | Counts tokens and shortens the context window if necessary. | `history` (str): The conversation history.<br>`*args`, `**kwargs`: Additional arguments. | `shortened_history = agent.count_and_shorten_context_window(history)` |
@@ -195,7 +194,6 @@ graph TD
 | `truncate_string_by_tokens(input_string, limit)` | Truncates a string to fit within a token limit. | `input_string` (str): String to truncate.<br>`limit` (int): Token limit. | `truncated_string = agent.truncate_string_by_tokens("Long string", 100)` |
 | `tokens_operations(input_string)` | Performs various token-related operations on the input string. | `input_string` (str): String to process. | `processed_string = agent.tokens_operations("Input string")` |
 | `parse_function_call_and_execute(response)` | Parses a function call from the response and executes it. | `response` (str): Response containing the function call. | `result = agent.parse_function_call_and_execute(response)` |
-| `activate_agentops()` | Activates AgentOps functionality. | None | `agent.activate_agentops()` |
 | `llm_output_parser(response)` | Parses the output from the language model. | `response` (Any): Response from the LLM. | `parsed_response = agent.llm_output_parser(llm_output)` |
 | `log_step_metadata(loop, task, response)` | Logs metadata for each step of the agent's execution. | `loop` (int): Current loop number.<br>`task` (str): Current task.<br>`response` (str): Agent's response. | `agent.log_step_metadata(1, "Analyze data", "Analysis complete")` |
 | `to_dict()` | Converts the agent's attributes to a dictionary. | None | `agent_dict = agent.to_dict()` |
@@ -484,10 +482,6 @@ agent.print_dashboard()
 # Fetch all the documents from the doc folders
 agent.get_docs_from_doc_folders()
 
-# Activate agent ops
-agent.activate_agentops()
-agent.check_end_session_agentops()
-
 # Dump the model to a JSON file
 agent.model_dump_json()
 print(agent.to_toml())

docs/swarms/install/env.md

@@ -528,8 +528,6 @@ agent.print_dashboard()
 agent.get_docs_from_doc_folders()
 
 # Activate agent ops
-agent.activate_agentops()
-agent.check_end_session_agentops()
 
 # Dump the model to a JSON file
 agent.model_dump_json()

docs/swarms/structs/agent.md

@@ -12,21 +12,23 @@
     agent_name="Financial-Analysis-Agent",
     agent_description="Personal finance advisor agent",
     system_prompt=FINANCIAL_AGENT_SYS_PROMPT,
-    max_loops="auto",
+    max_loops=2,
     model_name="gpt-4o",
     dynamic_temperature_enabled=True,
     user_name="swarms_corp",
     retry_attempts=3,
     context_length=8192,
     return_step_meta=False,
-    output_type="str",  # "json", "dict", "csv" OR "string" "yaml" and
+    output_type="all",  # "json", "dict", "csv" OR "string" "yaml" and
     auto_generate_prompt=False,  # Auto generate prompt for the agent based on name, description, and system prompt, task
     max_tokens=4000,  # max output tokens
     saved_state_path="agent_00.json",
     interactive=False,
     role="director",
 )
 
-agent.run(
-    "Create a table of super high growth opportunities for AI. I have $40k to invest in ETFs, index funds, and more. Please create a table in markdown.",
+print(
+    agent.run(
+        "Conduct an analysis of the best real undervalued ETFs. Think for 2 loops internally"
+    )
 )

docs/swarms/structs/agent_docs_v1.md

@@ -1,7 +1,7 @@
 from swarms.agents.agent_judge import AgentJudge
 
 
-judge = AgentJudge(model_name="gpt-4o", max_loops=1)
+judge = AgentJudge(model_name="gpt-4o-mini", max_loops=1)
 
 
 outputs = [

example.py

@@ -0,0 +1,21 @@
+from swarms.agents.gkp_agent import GKPAgent
+
+# Initialize the GKP Agent
+agent = GKPAgent(
+    agent_name="gkp-agent",
+    model_name="gpt-4o-mini",  # Using OpenAI's model
+    num_knowledge_items=6,  # Generate 6 knowledge items per query
+)
+
+# Example queries
+queries = [
+    "What are the implications of quantum entanglement on information theory?",
+]
+
+# Run the agent
+results = agent.run(queries)
+
+# Print results
+for i, result in enumerate(results):
+    print(f"\nQuery {i+1}: {queries[i]}")
+    print(f"Answer: {result}")